sminchev

Communication skills. IF you can't express yourself, the AI won't be able to understand you. I see in the morning subway, people don't talk, they watch their devices. A whole generation prefer to scroll in social media, instead of talking between each other. I am interested to see how they will use the prompts for express themselves in an understandable way, for professional purposes.

Model access: When using a Pro plan with Claude Code, you will only be able to use Opus models after enabling and purchasing extra usage.

Product Hunt, Beta List, Alternatives To, they are like polluted. And really valuable and meaningful products just can't excel, because people just can't see them. And this is pity. :(

I have not though about it from that angle. When I started developing 15-16 years ago, the IDEs were already here. I still use Eclipse daily. ;)

:) I do a similar app, for Android, but for elderly people. https://howareu.app/

A suggestion from my side is to add an option of detection based on stillness. If she is not able to press a button, that might mean that she is in trouble as well.

Not easy for all of us. It is a game-changer and we need to adapt. There will be a room for everybody, an AI development, and manual development.

There are places, where AI just can't be used, like banking, military, government projects. Banks can't just use AI. this is a big security leak for them. Of course, the need to developers will decrease, and a lot may lose their job. Just the demand will be less, compared with a few years ago.

I will give an example, I have all the tools to make a desk, but at the end I go to Ikea and buy it. In other words, people who does not have time and the needed expertise will always search for an external service.

Another example, in the beginning of car manufacturing, all was done by hand. Now, mostly is done by robots, but there are still cars that are manually made. The workers are not that much as before, but manual work is highly paid, and the provided quality is much bigger.

This is my prediction for the future, and I tell to myself, If I work hard, I will be one of those that 'produces car by hand'.

And also such changes can be quite motivating as well. Now it is an interesting time to search for a side project, as a back-up plan. Not the best time, because the market is polluted so much, but an interesting time, because quite a lot of ideas can now be implemented much easier, but with good quality.

I know. Just kidding with the daipers ;). I am conerned, at that age, working like I do it now won't be really possible, and that really might affect our monthly income and etc.

I am still in the phase of: Just released it, and fighting hard to make it working.

But mainly, a lot of things accumulated. I am 40 now, with two kids, the second - 6 months old. When she is 20, I will probably need to use daipers for elderly people. And she needs proper education.

AI is changing the world, and being a software developer might not be a safe long-term position anymore.

With my, almost 20 years of professional experience, as a software developer contractor, seeing a lot of project, I just felt confident enough to try. Let's see how it will go :)

I will you all the best in your journey :)

I think that you are underestimating the complexity. You need to deal with the specifics of different OEMs. You need to be absolutely sure that you are covering all cases, where the OEMs can stop the app. Testing and fine-tuning took more time, than I really expected

Then monitoring itself is not that easy as well. You need to distinguish between a planned vacation trip, and visit to a friend. And a lot, a lot more things.

To be honest, yes, it took me more time than expected. And now, with my current knowledge, next time, I will do it much, much faster, with less token. But this is how it is with every development. A junior developer will waste more time and money that an experienced one. With AI, most of us are like junior developers.

Most of the time, I waste, not with the app itself. But to keep it running 24/7, without in any way asking the parents to do any manual work. And this is because I did not know that Android based OSes are so aggressively killing long-running applications. I took my note :)

But to write it for a weekend, I just cannot agree. For a weekend, you can't make real and deep testing. A simple example: you need to run it for a few weeks, without opening it to see if Android will kill it, because it treats it as 'never used' app.

I doubt. Experience dev can't make 400+ files and write 2000 tests in a weekend. At least, I was never that fast and productive ;)

With my experience, developing android apps in Java, 10-15 years ago, such project would need at least 2 developers, for 5-6 months of development and testing.

:) It will be really stupid from my side to just let it go, without being sure that it will work. I am a professional after all, with almost 20 years of experience. There are 2000+ tests, 50K+ lines of testing code. I tested myself, and a lot of other people tested, with different devices. Covering all cases that we can think of. This is serious project, that I really hope that it will help a lot of people, and I really invested a lot of time and effort to make it stable. I intentionally delayed the push to production with a few weeks, so that I am 99.9% sure that I covered everything.

Of course, we are human after all, and I will highly appreciate every effort and support from others, so that we can make the product do better. :)

The idea is a children to install it on their parents devices and do nothing more. No smart watch, no need to the parents to frequently click anywhere. Just keep their device with them. I did it that way on purpose. To be as less intrusive as possible. The app stays there and run 24/7 and detect locations, moment of activeness and rest, sleep, and creates behavior patterns. If any of the pattern gets violated, it send a notification. I give an example: my father do a daily walk between 8AM and 10AM. If he misses that one I will receive a notification. If my mother fails on the street and she does not move for some time, I will receive a notification with the exact coordinates.

That simple ;)

Yes. you can't just leave it and go somewhere. Constant monitoring is required

Sometimes, people just have luck in the beginning. They have the idea, they implement it in the right moment, they find their clients fast, by luck. And those success stories stick, because people proudly talk about them. And there are people that work somewhere, see where the problem is find their customers there, and just continue by their own, providing better service.

But most people don't talk about their failures, because, maybe they are ashamed. In order to make a good product , the software development is just one peace of the cake. But in the technical universities, nobody teaches us marketing, and entrepreneurship, at least not in mine. ;) Those are the subject they explain about success stories, journeys, personas, financial aspects, support, marketing campaigns, specifics in other countries, laws, etc. You can easily see that the development is only a small part of the whole process.

You need a lot of time, a lot of books to read, and a lot of people to talk about: clients, partners, concurrents, etc.

And don't just use AI to give you answer. I tried to do a marketing campaign the way AI suggested, and I failed, because I did not have the proper basis to make the right decisions ;)

IF you don't check the code, you can't navigate correctly the UI. The AI is non-deterministic, and you can never be sure, that it will produce the same quality and use the same approach everytime. Even, with all the rules, lessons learned, documentation, a code review afterwards will find something. With that in mind, in order to write an assembler program, you need someone to teach the model how to do it. And in order to teach it, you need to be able to read what's generated ;)

So far, from source code perspective, I see good results. Things that yesterday Opus 4.6 was not able to fix in multiple iterations, today Opus 4.7 fixes immediately.

It is not only the model that affects the end results. Good technical specification, architecture documents, rules, lessons learned, release notes, proper and descriptive prompting are also important.

I have done integration it two applications: (1) I use it to analyze behavior, sleep and still patterns, and detect frequently visited locations, based on recorded and provided data. It is an monitoring app for elderly people; (2) suggestions, parsing files, as database. The first two are clear. The third, instead of supporting and maintaining a database, I call the AI to give me the information;

Used LLMs: Gemini 2.5 Flash. ChatGPT 5

I work task by task, like I usually do without AI agents. Working with multiple agents is just too much for me.

I have bmad integrated. and what I usually do for each session is: * call a start command that loads all the relevant documents and context; * call the bmad quick-dev or quick-spec slash commands that load an specialized agent. * at the end I update the documentation, commit, push, create pr, clear the session; * start from the beginning

If you do the above, and have enough basis as documentation, you can loose a little bit and let it run wildly, but like with human developers, some regular control might be needed. No way without it.

It is really, really difficult these days. There are so many project popping every day, and many people start to get annoyed. I already have stereotypes. When I read AI, I imagine: UAA (UI + API + AI architecture), and low quality, and sometimes I lose interest to continue reading.

In order a great idea to be distinguish from the the rubbish, a lot more efforts are needed today, compared with a few years ago, in my opinion.

Thank you for your question. At least there is one person who shares opinion, when down-voting. This is good, because I know what I did wrong, and I highly respect any respectable feedback ;)

I really hate, when people down-vote, without giving any feedback what they don't like.

Levenshtein, in combination with Machine Learning and big data engines, like Apache Sparks, can do a good job comparing content as well ;)

Wanted to share another approach, and ideas to people who are interested in comparing strings, doing fuzzy searches, and searching for duplicated content.

A few years ago, before the AI boom I needed to create a de-duplication app, as a PoC. To be able to compare fast millions of contact data and to search for the duplicates. The clients' approach was taking, in best case, a day to compare everything and generate a report.

What we do was a combination of big data engine, like Apache Spark, a few comparison algorithms like Levenshtein, and ML. AI was not treated as an option to do such things at all! :)

What we did was to use Apache Spark to apply the static algorithms, if we get confident results like less than 10% equality or more than 90% of equality, we treated those as sure signs for records be duplicated or not. Records that were somewhere in the middle, we sent to Machine Learning libraries for analysis. Of course some education was needed for statistical basis. And hard to be automatically analyzed, we placed in a report for human touch ;)

We got relatively good results. It was a Scala based app, as far as I remember :)

Now with AI, it is much more easy... And boring! :D No complexities, no challenges.

With such concurrency in the market, it is unforgivable to manage a product that way. The concurrency will kill you.

Clients get disappointed, alternatives have better services, and more are popping out monthly. If they continue that way, nothing good will happen, unfortunately :(

Sometimes, I really get bored, reading about AI products. At some point there are so many that look the same: UI + API + AI. I usually lose motivation when I don't see that the effort will give me good results or gains. 7 years ago I started learning Haskell, I read 2-3 book started working on a de-duplication app. At some point I realized that in order to learn the language to the level where I am confident that I know it, I need to practice it for at least an year, and afterwards, I need some miracle to happen to find a project and practice is. I decided that it does not worth the effort.

Now, the other case, I have a newborn. Now with two kids I am highly motivated. Also, with AI, not knowing a language is not a stopper anymore. So I made a pretty descent Android application for monitoring elderly people, that runs 24/7 despite Android is trying to kill it all the time, without practicing the language. Knowing that I can do it, seeing the results, having the responsibility sleeping behind me, gives me good reasons to continue. :)

Also what are our alternatives? Because of AI, I am not sure that I will have a job after one year. If I can do an android app with 400+ source files for 4 months, with 2000 unit tests, then it might happen that my employer reduces the working force, because there is not enough work for everybody. If don't have a back-up plan, what will I do?

If I still find myself tired and not motivated, I get another cup of coffee and continue :D :D

This is called concurrency and it drives the world forward. Why do we have so many producers and sellers of clothes. If we had only one clothes manifaturer in the world, who will trigger the innovation and progress forward?!

Nobody can steal your identity, attitude, communication with clients and support. And usually, this is what makes the difference.

And there are also other, legal ways to protect things, even though it is expensive. It is to patent your products and ideas. :)

How can I explain to my 6 months old girl that we all need to sleep :D

This is a bug in the universe! We need to sleep so that the levels of dopamine, and hormones of hunger and not hunger are at good levels, so that we can be healthy and strong, so that the immune system is stable and strong... And we need to get good sleep so that we can protect our children and be sane....

BUT the nature decided that the kids will wake up 3-4 times per night, and you need to wake up and take care of them.

You sleep in best case, on pauses, not more than 4-6 hours, you feel miserable, and at the same time you are THE HAPPIEST PERSON IN THIS WORLD! :)

Some people hate AI generated documentations, but we must get used to it. The statistics show it...

Nowadays, I can't distinguish between human written documentations and AI generated. I have seen people asking the AI to place a few typos so that the documentation looks more humanly written. Otherwise, they might get hated by others, being disrespectful.

The world is going crazy! :D

I watched a video a few years ago where one of Kent Beck, Martin Fowler, Jeff Sutherland, Ken Schwaber, I don't remember who exactly, explained what they wanted to do with the Agile Manifesto, what screwed up. He explained that they wanted to give guidelines, not a strict rules. They wanted flexibility. But people started selling this as courses, business, rules. Some Agile practitioners become fanatics on the topic. And this created misunderstanding and chaos :D

For 20 years, I have seen it working and not working, and the reasons are a lot. It can be affected of level of expertise, quality of documentation, pressure from management, engagement of the clients, etc.

Simple example of failing, and how one of my team overcome it. There is no specification. Option 1: team complains that the specification is bad, and this makes the code quality bad. Option 2: the team pro-actively prepared the specifications, gave them to the client for approval. Writing the specification was, a kind of, added flexibility, that was introduced in the sprints.

Another example, why should the sprints be fixed at 2 weeks. Sometimes, people try to finish for two weeks and they produce bad quality code, because they are time pressured. Be flexible and make them 3 weeks, if the sprint includes things like, preparing specifications, or if the sprint includes pauses for bug fixing. :)

So it is not the Agile that makes the project successful, it is the people. Agile just help for tracking where you are , and what you need to do ;)

Now with AI, you can use Agile again, there are agentic frameworks that support it and they give good results, in my opinion. If the people use it wisely, think what they do, and try to do things better, it will work. Of people are lazy, don't know what they are doing, don't have expertise on software development, it will fail :)

I know it is not fully in the scope, but I will describe my case, and I hope that this will give you some ideas and hits. I am working on an application that monitors elderly people in non-intrusive way. Their children install the application on their device and they do nothing with it. It follows the 'install and forget' principle. Don't bother them for anything. No notifications, no need to open it. If opening is needed, it is because they are curious, not because it is needed. All the information/notifications goes to their children. You can think in that direction. Can you make it a desktop application? In that case, you don't need authentication. It is actually simpler for them, because, instead of opening the browser, typing the URL, they just double click the icon. You can make a update mechanism that silently adds new features and bug fixes.

Some control can be added automatically from a server, so that they don't need to do anything.

The main problem here is, when they search for attention. I understand them and being respectful and giving them attention is a good thing, but from software support point of view, this is hard to be minimized.

The devices have their limits. We have those devices to make our life convenient. If we don't use the apps, it does not make sense to buy expensive phones that support so many features.

I will give you an example from recent weeks. I am a developer and I implemented a android app, all with AI, because Kotlin is not my language. But to make it working my expertise and skills to analyze, think of the architecture, security, databases, issues, debugging helped me make a stable product and I am really proud of the results. I got so confident that I thought I can do the marketing campaign with the same tools and success... AND I FAILED!!

Why? Because I don't know the basis, I can't decide what AI generated suggestion is good and what bad, what will work, and what won't work. Sometimes AI suggests things that are just not ethical. If I had a good basis, like in software development, I would have better results.

Yes, for sure, work will drop and it will affect some people, but web agencies will stay. I will give you another example. I have all the tools at home to make my own desk, but at the end of the day, I go to IKEA and buy a new from there ;) . I believe that the number of people needed to do a job will decrease, and the demanded quality will increase, because manual labor is more expensive. Because it is more expensive, it make sense clients to demand more for what they pay.

Time will show :)